Multi-objective optimal routing algorithm translation conversion theory subtitle translation research

At present, the traditional translation learning model lacks the construction of model network, which leads to low translation accuracy. In this paper, a multi-objective optimization routing algorithm is proposed to study Translation Shifts Theory subtitle translation. The multi-objective configuration method is used to optimize the parameters of the model, and the multi-objective constrained evolutionary feature solution is obtained by combining the semantic ontology feature decomposition method. The semantic association distribution model between ontologies is established, and the optimal output conversion control of English translation learning model is realized according to multi-objective optimization routing design. The experimental results show that the model has good convergence and high translation accuracy when this method is used in translation data processing, and this method has good performance.